© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41623
    Prev
    Next
    INDEX
    Explanations

    munch, slump, and mulch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ኧ
    -2.75
    u
    -2.44
    ꦥ
    -2.39
    </strong>
    -2.33
     you
    -2.28
    镞
    -2.22
    鸲
    -2.17
     Veränder
    -2.17
    躥
    -2.17
    🧌
    -2.16
    POSITIVE LOGITS
    '
    3.39
     avec
    2.23
    鱨
    2.17
    ↵
    2.11
    й
    2.09
     啦
    2.03
     \
    2.03
    ي
    2.00
    叫做
    1.95
    kwür
    1.93
    Activations Density 0.011%

    No Known Activations